DiffusionGemma cracks 1,500-token-per-second barrier with block-wise diffusion fine-tuned from Gemma-4
DiffusionGemma fine-tunes the 3.8B-parameter Gemma 4 with a two-stage diffusion pipeline, iteratively refining 256-token blocks in parallel. The result hits about 1,500 output tokens per second on one NVIDIA H100—far faster than autoregressive models—while keeping multimodal input, long-context support, and even near-AR quality.